© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 229
    Prev
    Next
    INDEX
    Explanations

    phrases indicating indirect objects or relative clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "that" and its variations, indicating a focus on clauses or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    which is qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    =")
    -0.52
    +-+-
    -0.51
    volles
    -0.51
    cive
    -0.50
    ered
    -0.50
    ]='\
    -0.50
    其中的
    -0.49
    fören
    -0.48
     ful
    -0.47
    iname
    -0.47
    POSITIVE LOGITS
     admittedly
    1.01
     obviously
    0.94
     unfortunately
    0.92
    obviously
    0.90
     thankfully
    0.89
     malheureusement
    0.88
     nobody
    0.86
     apparently
    0.86
     fortunately
    0.85
     obviamente
    0.85
    Activations Density 0.118%

    No Known Activations